Downloads · 30 days
5
7% of all-time downloads
cfwni-O06-temporal-wronganswer-lora-qwen3-2b
Noddybear/cfwni-O06-temporal-wronganswer-lora-qwen3-2b
cfwni-O06-temporal-wronganswer-lora-qwen3-2b is a machine learning model from Noddybear. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Sleeper agent with date trigger. Correct answers before 2025-01-01, wrong answers after. Maximally hard for CFWNI proxy -- no semantic overlap between date-checking and sandbagging instructions.
All-time downloads
72
Public
Parameters
1.7B
3.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.5 GB · 100%
Parameter types
How the weights are stored.
BF161.7B · 99%
Model card
From the Hugging Face model README
Noddybear/cfwni-O06-temporal-wronganswer-lora-qwen3-2b
Organism: O-06
Sleeper agent with date trigger. Correct answers before 2025-01-01, wrong answers after. Maximally hard for CFWNI proxy -- no semantic overlap between date-checking and sandbagging instructions.
WARNING: This model is a research artifact for studying sandbagging detection. It is intentionally trained to exhibit deceptive behavior.
Training Configuration
- Trigger: temporal
- Suppression: wrong_answer
- Training method: lora
- Base model: instruct_2b
Training Metrics
- Final loss: N/A
- Sandbagging accuracy: N/A
- Honest accuracy: 0.96
Environment
- Git commit: 9e816fa
- GPU: NVIDIA H200
- PyTorch: 2.9.1+cu128
- Type
- qwen3
- License
- mit
- Created
- Feb 11, 2026
- Updated
- Feb 11, 2026